PK
~XNt:+ + H
NLNZ-NZ-CRAWL-006-20170423083723646-04278-04287-wbgrp-crawl214_files.xmlUT _f_f
1492944083
1250
b8ead7d475bba7c0bd1014efd825d049
9a00d28e
6fa11302bfce8536b4a90655dc4a0c1156c406de
Text
true
1492945100
8816108
65bcfcb95935b9362c968b8a25df2272
217bf5e0
1c9c4c57e6ec05f47c668b6f49928f8d87ed6d42
Item CDX Index
true
1492945100
11375
22f9246a9e48691ecd12e4c4dbbe840f
400d8138
7dbba1ebd4bbc0cb738dcfc61bf01903c2c5ba46
Item CDX Meta-Index
true
Metadata
44fbfade232ea757c24ec7cd0c27538d
md5
1492944472
22528
Metadata
7b27c7d8190704bfad15997cad9b4912
2d6383d0
f042dc87ae27469dac120a11c9efd8790778a31a
1538257643
1745
Metadata
1ba63bd7bf55f8dd206e9c8af190ffa1
4060a7fc
b70e47c4f5078a4d65206cc8088847d461d569ae
1492944151
1000001586
fa85856b18e99a8dad7222a5d8f467dd
051a6d3e
63159ca6795f5d13ddbfd75f7d82adb0fa50b8cb
Web ARChive GZ
true
WARC CDX Index
NLNZ-NZ-CRAWL-006-20170423083723646-04278-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz
1492944719
925192
20c59d03d5fb3ebe84f39897df7aff3c
6982e76f
ae97dcc771154d954f346dcf1457baa24e66c2d2
true
1492944179
1003076729
fff13732b8bd12914d89c81f1cb05452
0ba95c28
9fe655600bff459c4edd4561e844522f65f02135
Web ARChive GZ
true
WARC CDX Index
NLNZ-NZ-CRAWL-006-20170423083822626-04279-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz
1492944761
966668
9888e2305cc681a4fb28937d4d6fdaf8
478747ee
81687fd1d465b2bcffa233fe1805749f6d28b86e
true
1492944206
1000030375
6f1ce73d667381650d5381e358dfef61
bd6ccc69
2b3c4fdbcdae8556db39141fbb0d79736012f6e1
Web ARChive GZ
true
WARC CDX Index
NLNZ-NZ-CRAWL-006-20170423084117068-04280-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz
1492944796
807252
d78adfba4c0376d56acd56fdfa4833cc
ff000546
a708d2695c4ed8588d74d35e69aa218bda82cf16
true
1492944240
1000009204
5ace26a259a97c2daa73ec828c20d0f5
a2c65947
4231e981f4888a48a62d5b852e46abd52b454a83
Web ARChive GZ
true
WARC CDX Index
NLNZ-NZ-CRAWL-006-20170423084920298-04281-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz
1492944841
1111959
6edbf9fb80a55f9e361fc53f9298e96c
91bfaef9
91f75ef19548484b9860b4e8f56dc93aca869244
true
1492944269
1000122962
667d6bec6bedc838134f12745a347b37
9c525d61
67da11d0adbe80b47fa972355aa1bb0d5efad5d8
Web ARChive GZ
true
WARC CDX Index
NLNZ-NZ-CRAWL-006-20170423085816290-04282-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz
1492944880
1005002
d8ae2db5b899beb396c1aa8b76dd1ee2
83f80d67
ea108b14d1e6b372e4547bf734c31f5fc2422969
true
1492944290
1000008657
e8ce6a794f46e20a9b13109dd3e3605b
cfb9aa36
c694024d2fcb6ce4ec09221ed693c2bb3cac6f88
Web ARChive GZ
true
WARC CDX Index
NLNZ-NZ-CRAWL-006-20170423090401348-04283-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz
1492944923
1030426
efe03f769b9e871bf0feda42ff3ff4fe
7ddbbfe8
16f1af8b0ca2a93f2e4ed98c34915ffc504c04c9
true
1492944314
1000040436
03fd8c3e2a2a2d410c2e44916d7550a2
c30fb2e4
6e6676d19fd15805253dcb736116071f6e7526f3
Web ARChive GZ
true
WARC CDX Index
NLNZ-NZ-CRAWL-006-20170423090410754-04284-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz
1492944960
906660
29fcfe5c36ebeb81ab372de2b575e624
554b1292
f0f544ce4b876934eac2d4d4c91373ce5c495531
true
1492944346
1002060461
93c32ac28490bbe013c8c76058ead0ef
448c020b
34410ca6af5ca7f927dd232ba7457ef645a7dc6a
Web ARChive GZ
true
WARC CDX Index
NLNZ-NZ-CRAWL-006-20170423091818815-04285-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz
1492944995
849401
805d67e6ce0ab2ef76110340accb2edd
a32fac45
8eda99c048871ed047aaa54e18a9a56d348bf21b
true
1492944387
1001565768
dfd69734b239996918e88a53d787dc82
df685de6
e1033a7523c373c230173d1104a1c62f9de90af9
Web ARChive GZ
true
WARC CDX Index
NLNZ-NZ-CRAWL-006-20170423092316951-04286-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz
1492945051
1452405
87ea89f79cd6714583bc6fc79762c88c
a01502a5
b5f7823afd82077f4fc301fabc9b9abdd7ae86da
true
1492944412
1000137679
90c964bc3803da9180181146659cac73
deeeffa3
09f4df182105817708ab5742c20ceb1f13675b8a
Web ARChive GZ
true
WARC CDX Index
NLNZ-NZ-CRAWL-006-20170423092814988-04287-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz
1492945089
997148
9b495c4bc7060355c025090716ea4bb5
0a1eaa9a
4d12b19024a0015d6ae9127a37afc6beda484063
true
PK
~X`@ G
NLNZ-NZ-CRAWL-006-20170423083723646-04278-04287-wbgrp-crawl214_meta.xmlUT _f_f
NLNZ-NZ-CRAWL-006-20170423083723646-04278-04287-wbgrp-crawl214
Internet Archive
Heritrix/3.3.0-SNAPSHOT-20160608-1933
NLNZ-NZ-CRAWL-006
Internet Archive
2017
Internet Archive crawldata from National Library of NEW ZEALAND, captured by wbgrp-crawl214.us.archive.org:NLNZ-NZ-CRAWL-006 from Sun Apr 23 08:37:23 PDT 2017 to Sun Apr 23 02:56:26 PDT 2017.
20170423083000
04278
https://archive.org/details/NLNZ-NZ-CRAWL-006-20170423083723646-04278-04287-wbgrp-crawl214
20170423025626
20170423095625
04287
web
10
adam@archive.org
20170423083000
wbgrp-crawl214.us.archive.org
sanfrancisco
10007053857
National Library of New Zealand
crawldata
NLNZ_Spring_2017 Crawldata 2017-04-23T08:37:23PDT to 2017-04-23T02:56:26PDT
NLNZ_Spring_2017
2017-04-23 10:41:24
webcrawl@archive.org
2017-04-23 10:41:24
nlnzweb
customcrawlservices
web
166672
ia906402_28
PK
~XЃc- X X J
NLNZ-NZ-CRAWL-006-20170423083723646-04278-04287-wbgrp-crawl214_meta.sqliteUT _f_fSQLite format 3 @ r r -
)A
NLNZ-NZ-CRAWL-006-20170423083723646-04278-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzETag: "fa85856b18e99a8dad7222a5d8f467dd"
accept: */*
authorization: LOW olRaGwdFJhutVLjb:REDACTED_BY_IA_S3
connection: close
content-length: 1000001586
content-md5: fa85856b18e99a8dad7222a5d8f467dd
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-archive-queue-derive: 0
x-ias3-encoded-key: NLNZ-NZ-CRAWL-006-20170423083723646-04278-23710%7Ewbgrp-crawl214.us.archive.org%7E8443.warc.gz
x-upload-date: 2017-04-23T10:42:31.000Z
A?!K
e e %y
MANIFEST.txtETag: "b8ead7d475bba7c0bd1014efd825d049"
accept: */*
authorization: LOW olRaGwdFJhutVLjb:REDACTED_BY_IA_S3
connection: close
content-length: 1250
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-amz-auto-make-bucket: 1
x-archive-meta-contributor: Internet Archive
x-archive-meta-crawler: Heritrix/3.3.0-SNAPSHOT-20160608-1933
x-archive-meta-crawljob: NLNZ-NZ-CRAWL-006
x-archive-meta-creator: Internet Archive
x-archive-meta-date: 2017
x-archive-meta-description: Internet Archive crawldata from National Library of NEW ZEALAND, captured by wbgrp-crawl214.us.archive.org:NLNZ-NZ-CRAWL-006 from Sun Apr 23 08:37:23 PDT 20
0 0pP 0 _ANLNZ-NZ-CRAWL-006-20170423092814988-04287-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz_ANLNZ-NZ-CRAWL-006-20170423092316951-04286-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz
_ANLNZ-NZ-CRAWL-006-20170423091818815-04285-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz _ANLNZ-NZ-CRAWL-006-20170423090410754-04284-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz_ANLNZ-NZ-CRAWL-006-20170423090401348-04283-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz_ANLNZ-NZ-CRAWL-006-20170423085816290-04282-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz_ANLNZ-NZ-CRAWL-006-20170423084920298-04281-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz_ANLNZ-NZ-CRAWL-006-20170423084117068-04280-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz_ANLNZ-NZ-CRAWL-006-20170423083822626-04279-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz_ANLNZ-NZ-CRAWL-006-20170423083723646-04278-23710~wbgrp-crawl214.us.archive.org~8443.warc.gz% MANIFEST.txt
H Hpu %99etables3item_pending_changess3item_pending_changesCREATE TABLE s3item_pending_changes
(
sequence_number INTEGER PRIMARY KEY ASC,
op blob,
args blob,
time float,
done int default 0
)))?tables3item_historys3item_historyCREATE TABLE s3item_history
(
sequence_number INTEGER PRIMARY KEY ASC,
key blob,
op blob,
data blob,
time float
);99tables3api_per_key_metadatas3api_per_key_metadataCREATE TABLE s3api_per_key_metadata
(
s3key blob,
headers blob,
live_date real,
old_version_of blob,
primary key (s3key),
unique (s3key)
)K_9 indexsqlite_autoindex_s3api_per_key_metadata_1s3api_per_key_metadata 17 to Sun Apr 23 02:56:26 PDT 2017.
x-archive-meta-firstfiledate: 20170423083723646
x-archive-meta-firstfileserial: 04278
x-archive-meta-identifier-access: https://archive.org/details/NLNZ-NZ-CRAWL-006-20170423083723646-04278-04287-wbgrp-crawl214
x-archive-meta-lastdate: 20170423025626
x-archive-meta-lastfiledate: 20170423092814988
x-archive-meta-lastfileserial: 04287
x-archive-meta-mediatype: web
x-archive-meta-numwarcs: 10
x-archive-meta-operator: adam@archive.org
x-archive-meta-scandate: 20170423083723
x-archive-meta-scanner: wbgrp-crawl214.us.archive.org
x-archive-meta-scanningcenter: sanfrancisco
x-archive-meta-sizehint: 10007053857
x-archive-meta-sponsor: National Library of New Zealand
x-archive-meta-subject: crawldata
x-archive-meta-title: NLNZ_Spring_2017 Crawldata 2017-04-23T08:37:23PDT to 2017-04-23T02:56:26PDT
x-archive-meta01-collection: NLNZ_Spring_2017
x-archive-queue-derive: 0
x-archive-size-hint: 10007053857
x-ias3-encoded-key: MANIFEST.txt
x-upload-date: 2017-04-23T10:41:24.000Z
A?!7
)A
NLNZ-NZ-CRAWL-006-20170423083822626-04279-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzETag: "fff13732b8bd12914d89c81f1cb05452"
accept: */*
authorization: LOW olRaGwdFJhutVLjb:REDACTED_BY_IA_S3
connection: close
content-length: 1003076729
content-md5: fff13732b8bd12914d89c81f1cb05452
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-archive-queue-derive: 0
x-ias3-encoded-key: NLNZ-NZ-CRAWL-006-20170423083822626-04279-23710%7Ewbgrp-crawl214.us.archive.org%7E8443.warc.gz
x-upload-date: 2017-04-23T10:42:59.000Z
A?!ZS
)A
NLNZ-NZ-CRAWL-006-20170423084117068-04280-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzETag: "6f1ce73d667381650d5381e358dfef61"
accept: */*
authorization: LOW olRaGwdFJhutVLjb:REDACTED_BY_IA_S3
connection: close
content-length: 1000030375
content-md5: 6f1ce73d667381650d5381e358dfef61
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-archive-queue-derive: 0
x-ias3-encoded-key: NLNZ-NZ-CRAWL-006-20170423084117068-04280-23710%7Ewbgrp-crawl214.us.archive.org%7E8443.warc.gz
x-upload-date: 2017-04-23T10:43:27.000Z
A?!`
)A
NLNZ-NZ-CRAWL-006-20170423084920298-04281-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzETag: "5ace26a259a97c2daa73ec828c20d0f5"
accept: */*
authorization: LOW olRaGwdFJhutVLjb:REDACTED_BY_IA_S3
connection: close
content-length: 1000009204
content-md5: 5ace26a259a97c2daa73ec828c20d0f5
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-archive-queue-derive: 0
x-ias3-encoded-key: NLNZ-NZ-CRAWL-006-20170423084920298-04281-23710%7Ewbgrp-crawl214.us.archive.org%7E8443.warc.gz
x-upload-date: 2017-04-23T10:44:00.000Z
A?!dDZ
)A
NLNZ-NZ-CRAWL-006-20170423085816290-04282-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzETag: "667d6bec6bedc838134f12745a347b37"
accept: */*
authorization: LOW olRaGwdFJhutVLjb:REDACTED_BY_IA_S3
connection: close
content-length: 1000122962
content-md5: 667d6bec6bedc838134f12745a347b37
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-archive-queue-derive: 0
x-ias3-encoded-key: NLNZ-NZ-CRAWL-006-20170423085816290-04282-23710%7Ewbgrp-crawl214.us.archive.org%7E8443.warc.gz
x-upload-date: 2017-04-23T10:44:29.000Z
A?!gR
)A
NLNZ-NZ-CRAWL-006-20170423090401348-04283-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzETag: "e8ce6a794f46e20a9b13109dd3e3605b"
accept: */*
authorization: LOW olRaGwdFJhutVLjb:REDACTED_BY_IA_S3
connection: close
content-length: 1000008657
content-md5: e8ce6a794f46e20a9b13109dd3e3605b
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-archive-queue-derive: 0
x-ias3-encoded-key: NLNZ-NZ-CRAWL-006-20170423090401348-04283-23710%7Ewbgrp-crawl214.us.archive.org%7E8443.warc.gz
x-upload-date: 2017-04-23T10:44:51.000Z
A?!
)A
NLNZ-NZ-CRAWL-006-20170423090410754-04284-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzETag: "03fd8c3e2a2a2d410c2e44916d7550a2"
accept: */*
authorization: LOW olRaGwdFJhutVLjb:REDACTED_BY_IA_S3
connection: close
content-length: 1000040436
content-md5: 03fd8c3e2a2a2d410c2e44916d7550a2
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-archive-queue-derive: 0
x-ias3-encoded-key: NLNZ-NZ-CRAWL-006-20170423090410754-04284-23710%7Ewbgrp-crawl214.us.archive.org%7E8443.warc.gz
x-upload-date: 2017-04-23T10:45:15.000Z
A?!P
) A
NLNZ-NZ-CRAWL-006-20170423091818815-04285-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzETag: "93c32ac28490bbe013c8c76058ead0ef"
accept: */*
authorization: LOW olRaGwdFJhutVLjb:REDACTED_BY_IA_S3
connection: close
content-length: 1002060461
content-md5: 93c32ac28490bbe013c8c76058ead0ef
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-archive-queue-derive: 0
x-ias3-encoded-key: NLNZ-NZ-CRAWL-006-20170423091818815-04285-23710%7Ewbgrp-crawl214.us.archive.org%7E8443.warc.gz
x-upload-date: 2017-04-23T10:45:46.000Z
A?!
)
A
NLNZ-NZ-CRAWL-006-20170423092316951-04286-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzETag: "dfd69734b239996918e88a53d787dc82"
accept: */*
authorization: LOW olRaGwdFJhutVLjb:REDACTED_BY_IA_S3
connection: close
content-length: 1001565768
content-md5: dfd69734b239996918e88a53d787dc82
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-archive-queue-derive: 0
x-ias3-encoded-key: NLNZ-NZ-CRAWL-006-20170423092316951-04286-23710%7Ewbgrp-crawl214.us.archive.org%7E8443.warc.gz
x-upload-date: 2017-04-23T10:46:27.000Z
A?!z,
q s)M q l A
NLNZ-NZ-CRAWL-006-20170423091818815-04285-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzputA?!;\l A
NLNZ-NZ-CRAWL-006-20170423090410754-04284-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzputA?!&l A
NLNZ-NZ-CRAWL-006-20170423090401348-04283-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzputA?!#l A
NLNZ-NZ-CRAWL-006-20170423085816290-04282-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzputA?!gvel A
NLNZ-NZ-CRAWL-006-20170423084920298-04281-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzputA?!dh#l A
NLNZ-NZ-CRAWL-006-20170423084117068-04280-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzputA?!aAl A
NLNZ-NZ-CRAWL-006-20170423083822626-04279-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzputA?!Zyl A
NLNZ-NZ-CRAWL-006-20170423083723646-04278-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzputA?!K1Oa %
MANIFEST.txtputA?!8
$ $ l A
NLNZ-NZ-CRAWL-006-20170423092814988-04287-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzputA?!l
A
NLNZ-NZ-CRAWL-006-20170423092316951-04286-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzputA?!
AY
NLNZ-NZ-CRAWL-006-20170423092814988-04287-23710~wbgrp-crawl214.us.archive.org~8443.warc.gzETag: "90c964bc3803da9180181146659cac73"
accept: */*
authorization: LOW olRaGwdFJhutVLjb:REDACTED_BY_IA_S3
connection: close
content-length: 1000137679
content-md5: 90c964bc3803da9180181146659cac73
expect: 100-continue
host: s3.us.archive.org
user-agent: curl/7.35.0
x-ias3-encoded-key: NLNZ-NZ-CRAWL-006-20170423092814988-04287-23710%7Ewbgrp-crawl214.us.archive.org%7E8443.warc.gz
x-upload-date: 2017-04-23T10:46:53.000Z
A?!rPK-
~XNt:+ + H @ NLNZ-NZ-CRAWL-006-20170423083723646-04278-04287-wbgrp-crawl214_files.xmlUT _fPK-
~X`@ G @~+ NLNZ-NZ-CRAWL-006-20170423083723646-04278-04287-wbgrp-crawl214_meta.xmlUT _fPK-
~XЃc- X X J @2 NLNZ-NZ-CRAWL-006-20170423083723646-04278-04287-wbgrp-crawl214_meta.sqliteUT _fPK ~ 6